skywalkskills

CatalogueAI-Era Code Health

F2Ready

Agent-Readiness Audit

Scores whether a repository gives a coding agent enough convention, tests, and feedback to change it reliably.

What it examines

  • Written conventions an agent can follow
  • A template for the kind of change you want repeated
  • Whether the code already follows one pattern
  • Tests an agent can run and trust
  • A fast way to know a change failed
  • Constraints the architecture actually enforces
  • Module boundaries that are visible in the tree

What you get back

A findings file. Each item has the evidence, how serious it is, and a fix.

Dependencies

  • An AI coding agent that reads SKILL.md files, such as Claude Code, Codex or Gemini CLI
  • Read access to the repository
  • Permission to run the repository’s own build, lint, test and type-check commands. The audit times them and asks before running anything with unclear side effects.
  • A short note on where agents go wrong in this repository today, if you have one
  • Python 3, for the report script. It uses only the standard library.
  • Python 3 with the jsonschema package, to check findings.json before fixing anything

How it works

The audit scores the repository from 0 to 3 on seven readiness dimensions, using what is really there: conventions, templates, tests, feedback loops and written constraints.

It reads the repository and runs your own commands to time them. It does not edit source or configuration.

If you described a symptom, such as an agent that keeps inventing new error handling, it traces that symptom back to the dimension that causes it.

You get a scorecard that lists every dimension, plus findings for the gaps that cost you something, ranked by that cost. The remediate skill reads findings.json and fixes or plans the selected gaps.

Setup

  1. Unzip the download, then copy the audit and remediate folders into your agent's skills folder (for Claude Code, .claude/skills/) in the repository you want to check.
  2. Write down where agents go wrong in this repository. One or two sentences is enough.
  3. Open the repository in your agent and ask it to run the f2-agent-readiness-audit skill. Approve the build and test commands it asks about.
  4. Check the result with the validator: pip install jsonschema, then python3 schema/validate.py findings.json.
  5. Ask your agent to run the f2-agent-readiness-remediate skill using findings.json.

Run it with your agent

Copy the prompt, fill in the parts in square brackets, and paste it into your agent.

Audit prompt

Run the f2-agent-readiness-audit skill on this repository. Where agents go wrong here today: [one or two sentences]. You may run the build, lint and test commands, and tell me first about anything with unclear side effects. Mode: audit only. Do not change any code. Write findings.json and findings.md in the repository root.

Fix prompt, after you have findings.json

Run the f2-agent-readiness-remediate skill using findings.json. Work through the findings I choose, and leave the rest open.

What is inside

The files that make up this skill, as your agent reads them.

packages/f2-agent-readiness

audit › SKILL.md

Sign in to download

Use the email and password you signed up with.